Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →majiayu000/review-agents-md
Creates minimal, effective AGENTS.md files using progressive disclosure.
Passed 21 of 22 test cases with the skill, and 11 of 22 without it.
and 7 more in the full report
11 fixed10 passed either way0 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
Write a line for AGENTS.md explaining our authentication architecture, choosing between specifying 'Auth logic lives in src/services/auth/' versus describing functional capability.
| Checked | Without skill | With skill |
|---|---|---|
| Describes the authentication capability rather than specifying the file path location | Missed | Passed |
The instructions your model reads when the skill loads.
Creates and refactors AGENTS.md files following progressive disclosure principles. Keeps files minimal and focused—avoiding the "ball of mud" that hurts agent performance.
AGENTS.md at the root — check for this when starting work in a new projectAGENTS.md exists but CLAUDE.md is missing (should be symlinked)Frontier LLMs can follow ~150-200 instructions with reasonable consistency. Every token in AGENTS.md loads on every request, regardless of relevance. The ideal file should be as small as possible.
Agent does something wrong → you add a rule → repeat hundreds of times → "ball of mud." Different developers add conflicting opinions. Nobody does a full style pass. Auto-generated files make this worse by prioritizing comprehensiveness over restraint.
Humans can be skeptical of outdated docs. Agents can't — they trust what they read on every request. File paths are especially dangerous since they change constantly. Describe capabilities and domain concepts instead.
Check the project root for AGENTS.md and CLAUDE.md:
test cases passed, vs 11 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.